Morphogen interpretation: concentration, time, competence, and signaling dynamics

Abstract

Tissue patterning during animal development is orchestrated by a handful of inductive signals. Most of these developmental cues act as morphogens, meaning they are locally produced secreted molecules that act at a distance to govern tissue patterning. The iterative use of the same signaling molecules in different developmental contexts demands that signal interpretation occurs in a highly context-dependent manner. Hence the interpretation of signal depends on the specific competence of the receiving cells. Moreover, it has become clear that the differential interpretation of morphogens depends not only on the level of signaling but also the signaling dynamics, particularly the duration of signaling. In this review, we outline molecular mechanisms proposed in recent studies that explain how the response to morphogens is determined by differential competence, pathway intrinsic feedback, and the interpretation of signaling dynamics by gene regulatory networks. WIREs Dev Biol 2017, 6:e271. doi: 10.1002/wdev.271 For further resources related to this article, please visit the WIREs website.

Figure 1

Differential competence for morphogen interpretation resides in the gene expression profile of receiving cells. (a) Scheme of a Drosophila wing disc displaying the subdivision into anterior and posterior compartments. The posterior compartment (blue) is characterized by expression of engrailed (en) and hedgehog (hh). Secreted Hh protein diffuses anteriorly, where it signals in a small stripe of cells (red). (b) En in the posterior compartment represses expression of ci, the transcriptional mediator of the Hh pathway. In contrast, cells in the anterior compartment express ci and can therefore activate Hh signaling. Hh binds and thereby inhibits the activity of Ptc (red), which relieves inhibition of Smo (blue). Smo activity blocks the proteasomal degradation of full‐length ci (CiFL) to its repressor form (CiR) and instead activates ci to promote the expression of Hh target genes. (c) Tissue specific activation of target genes by recruitment of transcriptional effector proteins (red hexagons, e.g. Gli) to specific binding sites in the genome by tissue specific cofactors (green and blue ellipses, e.g. SoxB family members in the neural tube). (d) Tissue specific inhibition of target genes by TFs that block the access of transcriptional effectors to specific binding sites (e.g. REST in non‐neuronal cells). Absence of these TFs leads to target gene activation. (e) Scheme of a zebrafish embryo at mid‐epiboly. (f) Nodal signaling in cells activates expression of Nodal ligands Ndr1/2 and the pathway inhibitors Lft1/2. The temporal competence window for Nodal signaling arises by miR430 delaying the translation of the pathway inhibitors Lft1/2. (g) Nodal signaling from the yolk syncytial layer (yellow) initially induces Ndr1/2 expression in cells directly at the margin (t ₁). Nodal signaling then spreads to its immediate neighbors, where it induces expression of Nodal ligands (t ₂, t ₃). This sequential induction of Nodal ligands and signaling results in a temporal gradient of Nodal signaling in marginal cells. The window for further spreading of Nodal signaling is terminated when Lft1/2 translation overcomes inhibition by miR430 (t ₄). (h) The differential competence for FP induction in response to Shh is mediated by opposing FGF and RA gradients along the anterior–posterior axis of the embryo. High levels of FGF signaling in the tail bud promote expression of Nkx1.2 (left). Combined activity of Nkx1.2 and Shh signaling in ventral parts of the neural tube induce the expression of FoxA2, which specifies FP cells (middle left). As cells are displaced anteriorly during development, they start to express Pax6 and Irx3 in response to RA, which then represses Nkx1.2 (middle right). Shh signaling in Pax6/Irx3 expressing cells induces expression of ventral neural progenitor markers Olig2 and Nkx2.2 (right).

Figure 2

Spatially dynamic morphogen expression. (a) Wg expression (red) initially broadly expressed in the Drosophila wing pouch recedes to the DV boundary during development. (b) A temporal gradient of Wg expression in the wing disc underlies the complete rescue of wing patterning by a nondiffusible Wg version. (c) Formation of a fgf8 mRNA gradient during axis elongation in vertebrate embryos. Expression of the fgf8 is restricted to posterior regions of the tail bud (violet). As cells get displaced anteriorly during axis elongation they carry fgf8 mRNA with them, leading to a fgf8 mRNA gradient (cyan). This gradient is continuously translated into a gradient of FGF8 protein (red). (d) Levels of fgf8 gene expression (violet), fgf8 mRNA (cyan), and FGF8 protein at different distances from the tail bud.

Figure 3

Pathway adaptation as means to measure signaling duration and dynamics. (a) The ventral neural tube is subdivided into different progenitor domains (p0–p3 and pMN) which form distinct classes of interneurons (V0–V3) and motor neurons. Subdivision of the three most ventral progenitor domains (p2, pMN, p3) is controlled by the differential expression of Irx3 (p2 only), Pax6 (p2, low in pMN), Olig2 (pMN), and Nkx2.2 (p3). This pattern is established in response to the graded activity of Shh, which generates two opposing gradients of activated Gli (GliA) and Gli repressor (GliR). (b) Due to pathway intrinsic negative feedback, different levels of Shh signaling are converted into distinct durations of Shh pathway activity. (c) Pathway intrinsic negative feedback leads to Shh pathway adaptation. In the absence of ligand (t ₁), Ptch1 receptors block the entrance of Smo to the primary cilium. This leads to proteasomal degradation of full‐length Gli (GliFL) into its repressor version (GliR). Upon exposure to Hh ligands (t ₂), Hh binds to Ptch1 and inhibits its activity, so Smo can enter into the cilium. Smo activity blocks Gli processing leading to stabilization and activation of GliFL, which activates target genes in the nucleus. Among the target genes of Gli are Hhip1 and Ptch1, which encode negative regulators of Hh pathway activity. Consequently, levels of Hh ligands need to rise continuously to inactivate increasing concentrations of Hhip1 and Ptch1 receptor (t ₃). Failure to do so, results in sequestration of Hh ligands and inactivation of the pathway (t ₄). (d) Pathway adaptation can be used to measure the speed of ligand exposure in the TGFβ pathway. In the absence of ligand, TGF receptors do not dimerize and Smad2/3 stay bound to the receptors (t ₁). Upon ligand binding, receptors dimerize, and phosphorylate Smad2/3, which allows dissociation of phosphorylated Smad2/3 from the receptor, interaction with Smad4 in the cytoplasm, nuclear accumulation, and activation of target genes (t ₂). Despite continuous exposure to the ligand, Smads are transported from the nucleus after a certain amount of time, leading to pathway adaptation (t ₃). (e) Pathway adaptation can be used to measure the speed of ligand exposure. Fast exposure of ligand (solid black line) leads to high levels of signaling (dashed black line) before the pathway adapts. In contrast, the response to slower ligand exposure (gray lines) is dampened by pathway adaptation.

Figure 4

Interpretation of signaling dynamics by gene regulatory networks. (a) Autoregulatory feed‐forward loop. (b) Autoregulatory feed‐forward loops can maintain gene expression domains in growing tissues. In the neural tube, dorsal Pax3 expression is initially induced in response to Wnt signaling, but maintains its own expression as the tissue grows and exceeds the size that can be stably patterned by a morphogen gradient.109 (c) Measurement of signal duration by a cascade of feed‐forward loops. Induction of target genes at every step depends on target genes induced previously by the same signal. Thus, target genes induced late in the cascade depend on longer duration of signaling. (d) Mutual cross‐repression of two TFs induced by the same signal. (e) Mutual cross‐repression usually results in the formation of sharp boundaries between gene expression domains. Thus, it provides a way to convert graded input into binary expression of target genes. (f) Mutual cross‐repression usually results in bistability and hysteresis (memory of the signal). Initially, high levels of signaling input are required to induce TF1 as repression of TF1 by TF2 must be overcome (lower line). However, once TF1 is induced much lower levels of signaling are required to maintain its expression as TF2 is repressed by TF1. Thus, there is a region of bistability (green) in which the same level of input favors expression of either TF1 or TF2 depending on the initial conditions. Such a mechanism is useful for maintaining gene expression domains induced in response to adapting signaling pathways or in growing tissues. (g) Gene regulatory network controlling the subdivision of the ventral neural tube into p2, pMN, and p3 progenitor domains in response to Shh signaling (see also Figure 3(a)). (h) Gene expression profile in response to increasing levels of Shh signaling. Upon small increase of Shh signaling, the transcriptional circuit favors expression of Olig2 (orange). In contrast, high levels of Shh signaling lead to expression of Nkx2.2 (red). (i) Temporal dynamics of gene expression for Shh levels favoring Nkx2.2 expression in (h). Although the transcriptional circuit favors Nkx2.2 expression at steady state, it moves through a transient phase with high levels of Olig2 expression. (j) Phase portrait illustrating the connection between levels and duration of Shh signaling for the induction of Olig2 and Nkx2.2 in the ventral neural tube. Induction of Nkx2.2 does not only depend on high levels of Shh pathway activity, but also long duration of signaling.